Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,388 indexed, measured the same four ways as everything else here.
Use when working on an agent task where AdaMAST failure-mode checkpoints, final submission gates, trace capture, taxonomy generation/refinement, or AdaMAST CLI setup should guide Codex. This skill helps Codex apply AdaMAST during software or research tasks, diagnose its own trajectory against the active taxonomy, and…
Create distill-style interactive explainers - single-file, zero-dependency HTML with hand-built Canvas figures - from documents, web research, or a codebase, with a fact-checking gate that supports, corrects, or cuts every claim.
★not rated 20 2mo agoA
tokens not measured
originalMIT
Compose a long-form pin-point lesson from one paper and register it as a Zotero child note. Use when the user provides a PDF or paper title and wants a math-grounded, idea-genealogy, fundamental-why analysis rather than a quick summary. Contrast with the summary skill, which produces a shorter overview note.
A tool that turns an agent’s progress, debugging notes, analysis, comparisons, or decisions into one self-contained HTML page. The page is designed for a person to review in a browser.
Marketing content pipeline with claim provenance and brand compliance: scan the codebase for product truth, write copy against it, enforce rules mechanically, render cards (PNG) and video (MP4) in the host repo's own brand.
★not rated 20 1mo agoA
tokens not measured
originalMIT
Agentic-use and skill-routing workflow for the Research Project Template. USE WHEN discovering relevant skills, making template easier for agents to navigate, auditing docs/prompts skill coverage, checking .cursor/skillmanifest.json, evaluating external skills, reviewing external agentic operating models such as…
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
★not rated 20 3d agoASkillSpector: pass61 tokens
originalMIT
Make product promo videos in the Claude video team style — terracotta canvas, macOS terminal window, animated Claude Code session — with Remotion. Use when the user asks for a product/feature promo, launch video, terminal demo video, or a "Claude-style" video.
Tunnistaa ja poistaa AI-generoidun suomenkielisen tekstin tunnusmerkit. Tekee tekstistä luonnollisempaa ja ihmisen kirjoittaman kuuloista. Käytä pyyntöihin humanisoimaan tai "tee paremmaksi".
Personal finance system as Claude skills: sync bank, document, and IBKR evidence into SQLite, and explore it in a live local React dashboard. Skills: setup, fetch-bank-data, fetch-investments, sync-finance-data, and findash-doctor.
★not rated 20 1mo agoA
tokens not measured
originalMIT
Generate an evidence-backed Assumptions ledger for a Git diff, feature, endpoint, worker, migration, or code path. Use when reviewing a change, asking what could break, preparing a release, finding edge cases, assessing deployment safety, analyzing retries or concurrency, or designing failure-focused tests.
Use when running Beastmode: director keeps design and merge; Luna Max does mechanical slices.
★not rated 20
changed 6d agoA0 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: